CATSE: A Context-Aware Framework for Causal Target Sound Extraction

no code implementations • 21 Mar 2024 • Shrishail Baligar, Mikolaj Kegler, Bryce Irvin, Marko Stamenovic, Shawn Newsam

First, we explore the utility of context by providing the TSE model with oracle information about what sound classes make up the input mixture, where the objective of the model is to extract one or more sources of interest indicated by the user.

Target Sound Extraction